Pith. sign in

REVIEW 10 cited by

Reuse and Diffuse: Iterative Denoising for Text-to-Video Generation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2309.03549 v1 pith:DQ7T6P7B submitted 2023-09-07 cs.CV cs.AIcs.MM

Jiaxi Gu , Shicong Wang , Haoyu Zhao , Tianyi Lu , Xing Zhang , Zuxuan Wu , Songcen Xu , Wei Zhang
show 2 more authors
Yu-Gang Jiang Hang Xu
This is my paper · ORCID
classification cs.CVcs.AIcs.MM
keywords framesvideodatasetslatentadditionaldiffusediffusionexisting
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

Inspired by the remarkable success of Latent Diffusion Models (LDMs) for image synthesis, we study LDM for text-to-video generation, which is a formidable challenge due to the computational and memory constraints during both model training and inference. A single LDM is usually only capable of generating a very limited number of video frames. Some existing works focus on separate prediction models for generating more video frames, which suffer from additional training cost and frame-level jittering, however. In this paper, we propose a framework called "Reuse and Diffuse" dubbed $\textit{VidRD}$ to produce more frames following the frames already generated by an LDM. Conditioned on an initial video clip with a small number of frames, additional frames are iteratively generated by reusing the original latent features and following the previous diffusion process. Besides, for the autoencoder used for translation between pixel space and latent space, we inject temporal layers into its decoder and fine-tune these layers for higher temporal consistency. We also propose a set of strategies for composing video-text data that involve diverse content from multiple existing datasets including video datasets for action recognition and image-text datasets. Extensive experiments show that our method achieves good results in both quantitative and qualitative evaluations. Our project page is available $\href{https://anonymous0x233.github.io/ReuseAndDiffuse/}{here}$.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. OmniCustom: Sync Audio-Video Customization Via Joint Audio-Video Generation Model

    cs.SD 2026-02 conditional novelty 6.0 of 10

    A zero-shot model that generates a video of a reference face speaking user-chosen text with a reference voice timbre.

  2. LoViC: Efficient Long Video Generation with Context Compression

    cs.CV 2025-07 conditional novelty 6.0 of 10

    LoViC uses FlexFormer, a single-query-token Q-Former with interpolated rotary positional encoding, to compress long video-text context for efficient long-video generation.

  3. FastInit: Fast Noise Initialization for Temporally Consistent Video Generation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A single-pass learned noise predictor, trained to imitate FreeInit's outputs, gives temporally more consistent text-to-video generation at near-zero added inference cost.

  4. Label-Efficient Data Augmentation with Video Diffusion Models for Guidewire Segmentation in Cardiac Fluoroscopy

    cs.CV 2024-12 reject novelty 6.0 of 10

    SF-VD generates labeled fluoroscopy videos via separate scene and motion diffusion models and reports improved guidewire segmentation, but test-set contamination weakens the evidence.

  5. Mind the Time: Temporally-Controlled Multi-Event Video Generation

    cs.CV 2024-12 conditional novelty 6.0 of 10

    MinT generates multi-event videos where each event's timing is controlled by the user, using a fine-tuned video diffusion transformer with a time-aware rotary position embedding.

  6. Multi-view Image Diffusion via Coordinate Noise and Fourier Attention

    cs.CV 2024-12 conditional novelty 6.0 of 10

    A diffusion method uses coordinate noise, time-dependent Fourier attention, and a cross-attention loss to improve multi-view consistency in generated images.

  7. AlayaWorld: Interactive Long-Horizon World Modeling - Full Technical Report (v1.1)

    cs.AI 2026-08 conditional novelty 5.0 of 10

    AlayaWorld v1.1 replaces depth-warped spatial memory with a streaming 3D point cache and aligns all conditioning signals to the causal VAE latent space, reporting the best WBench consistency score of 89.5.

  8. AlayaWorld: Long-Horizon and Playable Video World Generation

    cs.CV 2026-07 conditional novelty 4.0 of 10

    AlayaWorld is a full-stack open-source framework for interactive video world generation, combining 3D spatial caching, error-bank training, and few-step distillation for real-time playable worlds.

  9. Video Latent Flow Matching: Optimal Polynomial Projections for Video Interpolation and Extrapolation

    cs.CV 2025-02 reject novelty 4.0 of 10

    VLFM models video latent patches as a HiPPO-LegS polynomial flow and trains a flow matching model to generate frames, claiming bounded interpolation and extrapolation error.

  10. RichSpace: Enriching Text-to-Video Prompt Space via Text Embedding Interpolation

    cs.CV 2025-01 reject novelty 3.0 of 10

    Picking an interpolated text embedding with cosine similarity to a perpendicular foot can make a text-to-video model generate composite-feature videos that direct prompts miss.

Pith tools